© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20168
    Prev
    Next
    INDEX
    Explanations

    into [verb/noun phrase]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ients
    -0.10
    lesen
    -0.09
    æĢ¨
    -0.09
    åĿ¤
    -0.08
    尾巴
    -0.08
    asley
    -0.08
    -tabs
    -0.08
    ãģĴ
    -0.08
    çĶļ
    -0.08
     geh
    -0.08
    POSITIVE LOGITS
    çĶ¨èĩªå·±çļĦ
    0.09
    误
    0.09
    å°Ĩèĩªå·±çļĦ
    0.09
    onom
    0.09
    eren
    0.09
    鸥
    0.08
    çĺ´
    0.08
    çľĭçĤ¹
    0.08
    为åħ¶
    0.08
    失
    0.08
    Activations Density 0.013%

    No Known Activations